While relational representations have been popular in early work on syntactic and structural pattern recognition, they are rarely used in contemporary approaches to computer vision due to their pure symbolic nature. The recent progress and successes in combining statistical learning principles with relational representations motivates us to reinvestigate the use of such representations. More specifically, we show that statistical relational learning can be successfully used for hierarchical image understanding. We employ kLog, a new logical and relational language for learning with kernels to detect objects at different levels in the hierarchy. The key advantage of kLog is that both appearance features and rich, contextual dependencies between parts in a scene can be integrated in a principled and interpretable way to obtain a qualitative representation of the problem. At each layer, qualitative spatial structures of parts in images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures. We apply a four-layer hierarchy to street view images and successfully detect corners, windows, doors, and individual houses.

A Relational Kernel-Based Framework for Hierarchical Image Understanding / Laura Antanas; Paolo Frasconi; Fabrizio Costa; Tinne Tuytelaars; Luc De Raedt. - STAMPA. - 7626:(2012), pp. 171-180. (Intervento presentato al convegno International Workshops on Structural and Syntactic Pattern Recognition and Statistical Techniques in Pattern Recognition tenutosi a Hiroshima) [10.1007/978-3-642-34166-3_19].

A Relational Kernel-Based Framework for Hierarchical Image Understanding

FRASCONI, PAOLO;
2012

Abstract

While relational representations have been popular in early work on syntactic and structural pattern recognition, they are rarely used in contemporary approaches to computer vision due to their pure symbolic nature. The recent progress and successes in combining statistical learning principles with relational representations motivates us to reinvestigate the use of such representations. More specifically, we show that statistical relational learning can be successfully used for hierarchical image understanding. We employ kLog, a new logical and relational language for learning with kernels to detect objects at different levels in the hierarchy. The key advantage of kLog is that both appearance features and rich, contextual dependencies between parts in a scene can be integrated in a principled and interpretable way to obtain a qualitative representation of the problem. At each layer, qualitative spatial structures of parts in images are detected, classified and then employed one layer up the hierarchy to obtain higher-level semantic structures. We apply a four-layer hierarchy to street view images and successfully detect corners, windows, doors, and individual houses.
2012
Structural, Syntactic, and Statistical Pattern Recognition
International Workshops on Structural and Syntactic Pattern Recognition and Statistical Techniques in Pattern Recognition
Hiroshima
Laura Antanas; Paolo Frasconi; Fabrizio Costa; Tinne Tuytelaars; Luc De Raedt
File in questo prodotto:
File Dimensione Formato  
chp%3A10.1007%2F978-3-642-34166-3_19.pdf

Accesso chiuso

Tipologia: Altro
Licenza: Tutti i diritti riservati
Dimensione 1.25 MB
Formato Adobe PDF
1.25 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/790978
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 8
social impact